© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 9907
    Prev
    Next
    INDEX
    Explanations

    political references, focusing on interactions between Republicans and Democrats

    oai_token-act-pair · gpt-3.5-turbo

    references to political party dynamics and tensions between Republicans and Democrats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sterdam
    -0.95
     enqu
    -0.89
    teness
    -0.86
     metre
    -0.86
     catalogue
    -0.83
    awar
    -0.79
    utical
    -0.79
     analyse
    -0.79
    obyl
    -0.79
    mol
    -0.78
    POSITIVE LOGITS
     Republicans
    2.02
     Democrats
    2.00
    Republicans
    1.92
    Democrats
    1.88
     GOP
    1.83
     Dems
    1.74
     Republican
    1.66
     conservatives
    1.62
     Democratic
    1.61
    GOP
    1.60
    Activations Density 0.662%

    No Known Activations